End-to-End Kernel Learning with Supervised Convolutional Kernel Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

End-to-End Kernel Learning with Supervised Convolutional Kernel Networks


In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with supervision. We proceed by first proposing improvements of the recently-introduced convolutional kernel networks (CKNs) in the context of unsupervised learning; then, we derive backpropagation rules to take advantage of labeled training data. The resulting model is a new type of convolutional neural network, where optimizing the filters at each layer is equivalent to learning a linear subspace in a reproducing kernel Hilbert space (RKHS). We show that our method achieves reasonably competitive performance for image classification on some standard " deep learning " datasets such as CIFAR-10 and SVHN, and also for image super-resolution, demonstrating the applicability of our approach to a large variety of image-related tasks.
Fichier principal
Vignette du fichier
paper_supplement.pdf (12.61 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01387399 , version 1 (25-10-2016)


  • HAL Id : hal-01387399 , version 1


Julien Mairal. End-to-End Kernel Learning with Supervised Convolutional Kernel Networks. Advances in Neural Information Processing Systems (NIPS), Dec 2016, Barcelona, France. pp.1399-1407. ⟨hal-01387399⟩
944 View
809 Download


Gmail Facebook X LinkedIn More